nanochat now has a primordial identity and can talk a bit about itself and its capabilities (e.g. it knows it's nanochat d32 that cost $800, that it was built by me, that it can't speak languages other than English too well and why, etc.). This kind of customization is all done…
I fixed it :) deployed live now. This was done by doing a round of synthetic data generation to collect a 1000 multi-turn conversations (given a bunch of information including the readme of the nanochat project), and then mixing that into midtraining and SFT. fun!
In Rust, how the borrow-checker shapes your API inputs and outputs .. The general design principle is to choose signatures that minimize ownership churn while keeping call sites clean and safe. Accepting input • Borrow when you only read: `fn parse(src: &str)` • Borrow…
NVIDIA over USB4 on MacBook is ready to try! * ADT-UT3G dock + any 30/40/50 series GPU * Disable SIP * Install driver `extra/usbgpu/tbgpu` * Install NVK compiler `brew install tinymesa` * Test with: `DEBUG=2 NV_NAK=1 NV=1 python3 test/test_tiny.py TestTiny.test_plus`
Sharding. Database sharding is one of the common techniques to scale a database horizontally. You split the db into small parts called shards and distribute them across machines. Shards are typically in the few hundreds or even thousands (for extremely large databases). Usually…
(1/2) i felt like no one actually teaches you a good framework for how to read (ML) papers well + fast, so i wrote this 5-minute read tldr: because so many papers suck, here's how to go through them quickly and revisit the good ones
I just published the full guide to building forms with the Field component: - TanStack Form & React Hook Form - Zod validation and displaying errors - Practical examples we’ll actually use - Inputs, Radios, Fieldset, Arrays & more Check it out. Link below.
in the lectures below, i hold your hand through low-level LLM systems engineering. it includes everything up to TODAY! 1) pytorch tensors 2) large matmul on cpu vs gpu 3) JAX (and why xAI uses it instead of pytorch) 4) raw cuda kernels and global threading indexing 5) triton…
Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,…
My book simplifies Go internals as much as possible, so it's very easy to understand. If you still don't get it, it's Go's fault 🙈
I started at @thinkymachines today Looking forward to a lot of thoughtful work and thrilled to be contributing to their mission of advancing collective science
My favourite addition to prompts is: "Be extremely concise. Sacrifice grammar for the sake of concision." MUCH easier to scan, less reading overhead, cheaper to output. Before and after:
As an experiment I built a Mac trackpad multi-touch input visualizer. Saw someone mentioning that Unity has support for this. TBH this has been known for 16+ years now. It's basically an undocumented C API, which can be easily accessed via CGO. These API are not accessible via…
why isn't there lightweight, dev-friendly otel alternative written in rust yet?
United States 趨勢
- 1. #Talus_Labs N/A
- 2. Good Wednesday 28.7K posts
- 3. #wednesdaymotivation 5,301 posts
- 4. Hump Day 15.9K posts
- 5. #HeartQuakeMV 257K posts
- 6. $BYND 125K posts
- 7. ZEENUNEW CRAZY SINGLE 257K posts
- 8. Bwipo 1,450 posts
- 9. Usha Vance 9,878 posts
- 10. #Wednesdayvibe 1,962 posts
- 11. Howard University N/A
- 12. #13YearsofRed N/A
- 13. Izzo N/A
- 14. Beyond Meat 7,626 posts
- 15. Keke 5,827 posts
- 16. happy hump 10.4K posts
- 17. Froot N/A
- 18. St. John Paul 2,869 posts
- 19. Jen Psaki 11.7K posts
- 20. SEKI HONEYMOON X LINGORM 579K posts
Something went wrong.
Something went wrong.